Imagen de Portada

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Weiyang, Bai, Xuefeng, Chen, Kehai, Chen, Xinyang, Chen, Yibin, Guan, Weili, Zhang, Min
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning
por: Zhang, Hongbin, et al.
Publicado: (2024)

Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
por: Zhang, Hongbin, et al.
Publicado: (2025)

Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
por: Zhang, Hongbin, et al.
Publicado: (2024)

Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
por: Li, Zirui, et al.
Publicado: (2026)

DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
por: Chen, Andong, et al.
Publicado: (2024)

Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving
por: Chen, Andong, et al.
Publicado: (2024)

LLM-based Translation Inference with Iterative Bilingual Understanding
por: Chen, Andong, et al.
Publicado: (2024)

Efficient Reasoning with Balanced Thinking
por: Li, Yulin, et al.
Publicado: (2026)

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent
por: Li, Xingzuo, et al.
Publicado: (2025)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
por: Zhang, Xiaoyun, et al.
Publicado: (2025)

Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
por: Chen, Qiguang, et al.
Publicado: (2025)

Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
por: Zhang, Hongbin, et al.
Publicado: (2026)

MemLong: Memory-Augmented Retrieval for Long Text Modeling
por: Liu, Weijie, et al.
Publicado: (2024)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
por: Qian, Chen, et al.
Publicado: (2025)

MoK-RAG: Mixture of Knowledge Paths Enhanced Retrieval-Augmented Generation for Embodied AI Environments
por: Guo, Zhengsheng, et al.
Publicado: (2025)

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
por: Chen, Peter, et al.
Publicado: (2025)

Controlling Thinking Speed in Reasoning Models
por: Lin, Zhengkai, et al.
Publicado: (2025)

AdaThink-Med: Medical Adaptive Thinking with Uncertainty-Guided Length Calibration
por: Rui, Shaohao, et al.
Publicado: (2025)

StepWiser: Stepwise Generative Judges for Wiser Reasoning
por: Xiong, Wei, et al.
Publicado: (2025)

TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks
por: Kapoor, Vansh, et al.
Publicado: (2026)

Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM
por: Zhang, Shaoqing, et al.
Publicado: (2024)

ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
por: Li, Sunzhu, et al.
Publicado: (2025)

MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning
por: Chen, Hongwei, et al.
Publicado: (2025)

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
por: Guo, Zhenyuan, et al.
Publicado: (2026)

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
por: Yong, Xixian, et al.
Publicado: (2025)

Rubric-Guided Process Reward for Stepwise Model Routing
por: Ye, Shenghao, et al.
Publicado: (2026)

Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement
por: Liu, Chengyuan, et al.
Publicado: (2025)

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
por: Wan, Xu, et al.
Publicado: (2025)

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
por: Chen, Haoyang, et al.
Publicado: (2026)

nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning
por: Luo, Tianqi, et al.
Publicado: (2025)

Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent
por: Tang, Yihong, et al.
Publicado: (2026)

Reasoning Models Can Be Effective Without Thinking
por: Ma, Wenjie, et al.
Publicado: (2025)

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness
por: Jayarao, Pratik, et al.
Publicado: (2025)

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
por: Zhu, Jason, et al.
Publicado: (2025)

LLM-based Discriminative Reasoning for Knowledge Graph Question Answering
por: Xu, Mufan, et al.
Publicado: (2024)

DaSAThco: Data-Aware SAT Heuristics Combinations Optimization via Large Language Models
por: Chen, Minyu, et al.
Publicado: (2025)

SAFE: Stepwise Atomic Feedback for Error correction in Multi-hop Reasoning
por: Kwon, Daeyong, et al.
Publicado: (2026)

Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers
por: Chen, Xin, et al.
Publicado: (2026)

MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models
por: Jin, Bohan, et al.
Publicado: (2025)

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
por: Cui, Yingqian, et al.
Publicado: (2025)